Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    limited partnerships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     않았
    0.64
     Մ
    0.62
    ^*\
    0.61
     Це
    0.60
    先輩
    0.59
     \{
    0.59
    なかなか
    0.59
     ﺍ
    0.59
    ]【
    0.59
    телем
    0.58
    POSITIVE LOGITS
    ↵
    1.34
    ו
    1.10
    ,
    1.02
    ли
    0.93
    ও
    0.89
    .
    0.89
    م
    0.87
    在
    0.87
    도
    0.83
     can
    0.83
    Act Density 0.000%

    No Known Activations